Construction stage detection using satellite or aerial imagery

Abstract

Methods, non-transitory computer-readable storage media, and computer or computer systems directed to detecting, analyzing, and tracking stages of housing construction using satellite or aerial imagery in combination with a machine learned model are described.

1 . A method comprising:
 receiving a satellite or aerial image, or portion thereof, of a geographic area as input into a machine learned model trained with a set of satellite or aerial images having features characteristic of housing at one or more stages of construction and corresponding labels representing such stages;   determining from the machine learned model which features in the satellite or aerial image or portion thereof correspond to which stages of construction; and   sending an output from the machine learned model, the output comprising one or more predictions of the stages of construction determined for the features in the satellite or aerial image or portion thereof.   
     
     
         2 . The method of  claim 1 , wherein the machine learned model is a trained Convolutional Neural Network (CNN). 
     
     
         3 . The method of  claim 1 , wherein the one or more stages are chosen from stages comprising slab, foundation, under construction, and completed. 
     
     
         4 . The method of  claim 1 , wherein the machine learned model is stored on a non-transitory computer-readable memory. 
     
     
         5 . The method of  claim 1 , wherein the receiving, determining, and sending are performed by one or more processor. 
     
     
         6 . The method of  claim 1 , further comprising storing the satellite or aerial image, or portion thereof, of a geographic area on a non-transitory computer-readable memory. 
     
     
         7 . The method of  claim 1 , wherein the satellite or aerial image or portion thereof is received from a satellite or aerial imagery provider service. 
     
     
         8 . The method of  claim 1 , wherein the output comprises a probability that the identified feature represents a stage of construction. 
     
     
         9 . The method of  claim 1 , further comprising converting pixel locations in the satellite or aerial image or portion thereof to geographic coordinates, and outputting the geographic coordinates. 
     
     
         10 . The method of  claim 1 , wherein the output is displayed on the satellite or aerial image or portion thereof provided as input to the machine learned model. 
     
     
         11 . A method comprising:
 selecting a geographic area of interest on a map or satellite or aerial image;   causing a satellite or aerial image or portion thereof corresponding to the geographic area of interest to be sent as input for a machine learned model trained with a set of satellite or aerial images having features characteristic of housing at one or more stages of construction and corresponding labels representing such stages; and   receiving one or more output from the machine learned model, the output comprising one or more predictions of the stages of construction determined for the features in the satellite or aerial image or portion thereof.   
     
     
         12 . The method of  claim 11 , wherein the one or more stages are chosen from stages comprising slab, foundation, under construction, and completed. 
     
     
         13 . The method of  claim 11 , wherein the selecting and causing are based upon input from a user interface. 
     
     
         14 . The method of  claim 13 , wherein the input comprises one or more location information chosen from information comprising city, county, state, zip code, geographic coordinates and tax parcel number. 
     
     
         15 . The method of  claim 13 , wherein the input comprises providing an outline surrounding the geographic area of interest. 
     
     
         16 . The method of  claim 13 , wherein the one or more output is received by the user interface. 
     
     
         17 . The method of  claim 16 , wherein the one or more output is chosen from information comprising a boundary, a center point, geographic location, and stage of construction of houses in the satellite or aerial image or portion thereof. 
     
     
         18 . The method of  claim 11 , wherein the machine learned model is a trained Convolutional Neural Network (CNN). 
     
     
         19 . The method of  claim 11 , wherein the selecting, causing, and receiving are performed by one or more processors. 
     
     
         20 . A method comprising:
 extracting metadata from one or more satellite or aerial images having features characteristic of housing at one or more stages of construction stored in a first non-transitory computer readable memory;   cross-referencing geographic information present in the metadata with geographic information inputted as a selected geographic area of interest; and   receiving one or more of the satellite or aerial images from the first non-transitory computer readable memory for storage in a second non-transitory computer readable memory based upon common geographic information present in the metadata and the geographic area of interest.   
     
     
         21 . The method of  claim 20 , wherein the first non-transitory computer readable memory has stored thereon a library of satellite or aerial images provided by a satellite or aerial imagery provider service. 
     
     
         22 . The method of  claim 20 , further comprising determining a portion of the one or more satellite or aerial images to be received from the first non-transitory computer readable memory based upon a measurement of an intersection of the geographic area of interest with the satellite or aerial image area such that the determined portion of the one or more satellite or aerial images is received and stored in the second non-transitory computer readable memory. 
     
     
         23 . One or more non-transitory, computer-readable storage media having instructions for execution by the one or more processors, the instructions programmed to cause the one or more processors to:
 receive a satellite or aerial image, or portion thereof, of a geographic area as input into a machine learned model trained with a set of satellite or aerial images having features characteristic of housing at one or more stages of construction and corresponding labels representing such stages;   determine from the machine learned model which features in the satellite or aerial image or portion thereof correspond to which stages of construction; and   send an output from the machine learned model, the output comprising one or more predictions of the stages of construction determined for the features in the satellite or aerial image or portion thereof.   
     
     
         24 . The one or more non-transitory, computer readable storage media of  claim 23 , wherein the machine learned model is a trained Convolutional Neural Network (CNN) stored thereon. 
     
     
         25 . The one or more non-transitory, computer readable storage media of  claim 23 , wherein the one or more stages are chosen from stages comprising slab, foundation, under construction, and completed. 
     
     
         26 . One or more non-transitory, computer-readable storage media having instructions for execution by the one or more processors, the instructions programmed to cause the one or more processors to:
 select a geographic area of interest on a map or satellite or aerial image;   cause a satellite or aerial image or portion thereof corresponding to the geographic area of interest to be sent as input for a machine learned model trained with a set of satellite or aerial images having features characteristic of housing at one or more stages of construction and corresponding labels representing such stages; and   receive one or more output from the machine learned model, the output comprising one or more predictions of the stages of construction determined for the features in the satellite or aerial image or portion thereof.   
     
     
         27 . The one or more non-transitory, computer-readable storage media of  claim 26 , wherein the machine learned model is a trained Convolutional Neural Network (CNN). 
     
     
         28 . The one or more non-transitory, computer-readable storage media of  claim 26 , wherein the one or more stages are chosen from stages comprising slab, foundation, under construction, and completed. 
     
     
         29 . One or more non-transitory, computer-readable storage media having instructions for execution by the one or more processors, the instructions programmed to cause the one or more processors to:
 extract metadata from one or more satellite or aerial images having features characteristic of housing at one or more stages of construction stored in a first non-transitory computer readable memory;   cross-reference geographic information present in the metadata with geographic information inputted as a selected geographic area of interest; and   receive one or more of the satellite or aerial images from the first non-transitory computer readable memory for storage in a second non-transitory computer readable memory based upon common geographic information present in the metadata and the geographic area of interest.   
     
     
         30 . The one or more non-transitory, computer-readable storage media of  claim 29 , wherein the first non-transitory computer readable memory has stored thereon a library of satellite or aerial images provided by a satellite or aerial imagery provider service. 
     
     
         31 . The one or more non-transitory, computer-readable storage media of claim  292 , wherein the instructions are further programmed to cause the one or more processor to determine a portion of the one or more satellite or aerial images to be received from the first non-transitory computer readable memory based upon a measurement of an intersection of the geographic area of interest with the satellite or aerial image area such that the determined portion of the one or more satellite or aerial images is received and stored in the second non-transitory computer readable memory. 
     
     
         32 . A computer or computer system, comprising:
 one or more processors designed to execute instructions;   one or more non-transitory, computer-readable memories storing program instructions for execution by the one or more processors, the instructions programmed to cause the one or more processors to:
 receive a satellite or aerial image, or portion thereof, of a geographic area as input into a machine learned model trained with a set of satellite or aerial images having features characteristic of housing at one or more stages of construction and corresponding labels representing such stages; 
 determine from the machine learned model which features in the satellite or aerial image or portion thereof correspond to which stages of construction; and 
 send an output from the machine learned model, the output comprising one or more predictions of the stages of construction determined for the features in the satellite or aerial image or portion thereof. 
   
     
     
         33 . The computer or computer system of  claim 32 , wherein the machine learned model is a trained Convolutional Neural Network (CNN) stored on one or more of the non-transitory computer readable memories. 
     
     
         34 . The computer or computer system of  claim 32 , wherein the one or more stages are chosen from stages comprising slab, foundation, under construction, and completed. 
     
     
         35 . A computer or computer system, comprising:
 one or more processors designed to execute instructions;   one or more non-transitory, computer-readable memories storing program instructions for execution by the one or more processors, the instructions programmed to cause the one or more processors to:
 select a geographic area of interest on a map or satellite or aerial image; 
 cause a satellite or aerial image or portion thereof corresponding to the geographic area of interest to be sent as input for a machine learned model trained with a set of satellite or aerial images having features characteristic of housing at one or more stages of construction and corresponding labels representing such stages; and 
 receive one or more output from the machine learned model, the output comprising one or more predictions of the stages of construction determined for the features in the satellite or aerial image or portion thereof. 
   
     
     
         36 . The computer or computer system of  claim 35 , wherein the machine learned model is a trained Convolutional Neural Network (CNN) stored on one or more of the non-transitory computer readable memories. 
     
     
         37 . The computer or computer system of  claim 35 , wherein the one or more stages are chosen from stages comprising slab, foundation, under construction, and completed. 
     
     
         38 . A computer or computer system, comprising:
 one or more processors designed to execute instructions;   one or more non-transitory, computer-readable memories storing program instructions for execution by the one or more processors, the instructions programmed to cause the one or more processors to:
 extract metadata from one or more satellite or aerial images having features characteristic of housing at one or more stages of construction stored in a first non-transitory computer readable memory; 
 cross-reference geographic information present in the metadata with geographic information inputted as a selected geographic area of interest; and 
 receive one or more of the satellite or aerial images from the first non-transitory computer readable memory for storage in a second non-transitory computer readable memory based upon common geographic information present in the metadata and the geographic area of interest. 
   
     
     
         39 . The computer or computer system of  claim 38 , wherein the first non-transitory computer readable memory has stored thereon a library of satellite or aerial images provided by a satellite or aerial imagery provider service. 
     
     
         40 . The computer or computer system of  claim 38 , wherein the instructions are further programmed to cause the one or more processor to determine a portion of the one or more satellite or aerial images to be received from the first non-transitory computer readable memory based upon a measurement of an intersection of the geographic area of interest with the satellite or aerial image area such that the determined portion of the one or more satellite or aerial images is received and stored in the second non-transitory computer readable memory.